Translating Images to Road Network:A Non-Autoregressive Sequence-to-Sequence Approach

2 code implementations • 13 Feb 2024 • Jiachen Lu, Renyuan Peng, Xinyue Cai, Hang Xu, Hongyang Li, Feng Wen, Wei zhang, Li Zhang

Instead, our work establishes a unified representation of both types of data domain by projecting both Euclidean and non-Euclidean data into an integer series called RoadNet Sequence.

LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement

2 code implementations • 31 Jan 2024 • Renyuan Peng, Xinyue Cai, Hang Xu, Jiachen Lu, Feng Wen, Wei zhang, Li Zhang

Accurate extraction of lane graphs relies on precisely estimating vertex and edge information within the DAG.

Autonomous Driving Language Modelling

Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving

1 code implementation • 6 Dec 2023 • Ming Nie, Renyuan Peng, Chunwei Wang, Xinyue Cai, Jianhua Han, Hang Xu, Li Zhang

Large vision-language models (VLMs) have garnered increasing interest in autonomous driving areas, due to their advanced capabilities in complex reasoning tasks essential for highly autonomous vehicle behavior.

Autonomous Driving Decision Making

Translating Images to Road Network: A Non-Autoregressive Sequence-to-Sequence Approach

no code implementations • ICCV 2023 • Jiachen Lu, Renyuan Peng, Xinyue Cai, Hang Xu, Hongyang Li, Feng Wen, Wei zhang, Li Zhang

The extraction of road network is essential for the generation of high-definition maps since it enables the precise localization of road landmarks and their interconnections.